Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23208
    Prev
    Next
    INDEX
    Explanations

    technical specifications and model names in electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to different models and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estern
    -0.81
    racial
    -0.78
    speech
    -0.78
    arching
    -0.77
    partisan
    -0.75
     Speech
    -0.72
    orney
    -0.72
     Liberties
    -0.72
    ulty
    -0.72
    renched
    -0.71
    POSITIVE LOGITS
     versions
    0.91
     variants
    0.83
     upgr
    0.79
    Versions
    0.79
     jackets
    0.78
     configurations
    0.78
     manufacturers
    0.78
     incarnation
    0.77
     designation
    0.75
     fitted
    0.75
    Activations Density 0.115%

    No Known Activations